© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5708
    Prev
    Next
    INDEX
    Explanations

    technical terms in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ተግባ
    0.40
     നമ്മ
    0.39
    រួ
    0.38
    लापूर
    0.37
     জনাব
    0.37
    ಿದ್ದೇವೆ
    0.37
    álu
    0.36
    变成了
    0.36
     亠
    0.36
    ufthansa
    0.36
    POSITIVE LOGITS
    、
    1.17
    ،
    1.08
    ၊
    1.06
    ,
    1.02
    ፣
    0.98
    ‌,
    0.89
    ，
    0.88
     、
    0.87
     ፣
    0.85
     ,
    0.82
    Activations Density 0.370%

    No Known Activations